Copilot was bamboozled into revealing how to hack itself, security researchers claim: 'Copilot wasn’t breached; it was played'

Security researchers at Zenity claimed they tricked Microsoft's Copilot into revealing instructions for hacking itself, describing the exploit as 'Copilot wasn’t breached; it was played.' The researchers demonstrated that Copilot could be manipulated through prompt injection to disclose its own system prompts and security rules, highlighting a vulnerability in AI chatbot safeguards.

Join the club for quick access. Enter your email below and we'll send confirmation, and sign you up to our newsletter. By submitting your information, you confirm you are aged 16 or over, have read our Privacy Policy https://futureplc.com/privacy-policy/ and agree to the Terms & Conditions https://futureplc.com/future-member-terms-and-conditions/ . Geographical rules apply. Your membership journey starts here. Keep exploring and earning more as a member. Stay Ahead with PC Gamer Get the biggest gaming news, reviews, and releases straight to your inbox.